Taught in 2022–2023 by Benoît Crabbé and Philippe de Groote.
First semester course, on Thursdays 12:45–15:45 in room 1004. Classes delivered in English if at least one student asks for it; in French otherwise.
We sketch here the planned contents for 2022–2023.
These contents are structured around three important subdomains of
linguistics, (morphology, syntax, and semantics),
presenting on each occasion some of the related models and the
corresponding algorithmic issues. The exact dates and content might
change.
September 15th, 2022 (
slides)
General Introduction Language has structure. Language and inference. The importance of ambiguity. Language and the world.
Linguistics basics for computational linguistics. Statistical properties of words, constituent and dependency analyses, computing semantic denotations and computing semantic similarities.
Machine learning basics for computational linguistics. Coding discrete symbols as vectors (word embeddings), optimisation reminder.
September 29th, 2022 (
slides)
Modelling sequences Presentation of typical problems involving sequence modelling.
Generative models language models, hidden markov models, PCFG
Discriminative models conditional random fields
Algorithms Viterbi and approximative methods
Deep learning based methods
October 6th, 2022
Modelling syntax (
slides)
Phrase structure grammar
Tree adjoining Grammar
Dependency syntax
Categorial grammar
October 13th, 2022
Parsing algorithms for natural language(
slides
CKY and Earley Introduction to weighted CKY and Earley
Shift Reduce and Eisner for Dependency syntax
CKY for tree adjoining grammar
-
October 20th, 2022
November 2nd, 2022
November 10th, 2022
November 17th, 2022 Discourse Analysis discourse representation theory, anaphora resolution, type-theoretic dynamic logic
November 24rd, 2022